Blog

R Product 23 May 2026 · 3 min read Run ToRun on your own infrastructure — on-prem and self-hosted Not every team can send prompts to a third-party cloud. Regulated industries, government workloads, and companies with strict data-residency rules need their AI stack to stay inside their own network. ToRun ships as a se… B Product 22 May 2026 · 4 min read Build and run AI workflows on ToRun What a workflow actually is here Most "workflow" tools in the AI space are prompt chains with a thin wrapper. ToRun's builder is a directed acyclic graph DAG of typed steps: you connect model invocations, tool calls, con… L Product 21 May 2026 · 4 min read Long-term memory that actually persists — how ToRun remembers what matters Most AI products claim to "remember you." What they usually mean is that the current conversation window has not scrolled out of range yet. Once you close the tab, the model has no idea who you are. You re-explain your s… H Engineering 20 May 2026 · 5 min read How ToRun picks the right model for every message The problem with "just use GPT-4" Most AI platforms make a quiet choice on your behalf: they pick a model they like, wire everything to it, and move on. That works until it doesn't — until the model is down, until a comp… W Product 19 May 2026 · 4 min read What is ToRun? One honest home for all your AI Most AI tools have a core tension they never acknowledge: the best model for your task today may not be the same model tomorrow, yet you are expected to commit to one provider's subscription and work around its blind spo… B Security 18 May 2026 · 1 min read Bring-your-own-key — how ToRun keeps your credentials safe What BYOK means here Bring-your-own-key BYOK on ToRun lets you add your own provider API key on the BYOK page in your account. Calls that can use it go through your own provider account: the provider bills that account f… T Announcement 18 May 2026 · 1 min read ToRun Phase 1 is live — capability-first AI orchestration What shipped today Phase 1 of ToRun is now live. After eighteen months of platform work, we have flipped the switch on the capability-first orchestration model the team has been describing in roadmap calls all year. What… D Engineering 18 May 2026 · 2 min read Designing for multi-tenant SaaS — the ToRun approach Tenants, hosts, and the dataset filter ToRun is built on ABP Framework's multi-tenancy model. A row marked IsMultiTenant has a TenantId column that the framework filters automatically; queries from inside a tenant contex… U Engineering 18 May 2026 · 2 min read Understanding multimodal AI pricing — tokens, images, and seconds One BillingRecord per call, full snapshot Every AI call on ToRun produces exactly one BillingRecord that captures the price at the moment of execution. Provider rates change every few weeks; storing the rate inline means…